摘要
提出一种基于亚像素算法的混凝土结构表面裂缝宽度测量方法,对裂缝图像进行了对比度增强和降噪去噪处理,并提取裂缝图像上的裂缝特征;采用canny算子,对裂缝边缘整像素进行识别,利用它们在原裂缝图像上对应附近的灰度梯度,对基于亚像素精度的Gaussian曲线进行拟合,并计算出亚像素精度的边缘特征参数,实现了对裂缝宽度的测量。经实测,验证了该方法的测量精度。
A method of measuring the surface crack width of concrete structures based on sub-pixel algorithm is presented. The contrast enhancement and noise reduction of the crack image are carried out to extract the crack features on the image. The canny algorithm is carried out to get some edge points at pixel level,and try to get the gradient levels of points near them on the original crack image, and then Gaussian curve is used to fit the gradient levels of these points to achieve the accurate position of edge point with a subpixel precision,and then the width is calculated. The measurement precision of the method proposed is tested by actual measured value.
出处
《交通科学与工程》
2017年第4期31-36,共6页
Journal of Transport Science and Engineering
